Tool condition monitoring and machine tool diagnostics are performed using advanced sensors and computational intelligence to predict and avoid adverse conditions for cutting tools and machinery. Undesirable conditions during machining cause chatter, tool wear, and tool breakage, directly affecting the tool life and consequently the surface quality, dimensional accuracy of the machined parts, and tool costs. Tool condition monitoring is, therefore, extremely important for manufacturing efficiency and economics. Acoustic emission, vibration, power, and temperature sensors monitor the stability and efficiency of the machining process, collecting large amounts of data to detect tool wear, breakage, and chatter. Studies on monitoring the vibrations and acoustic emissions from machine tools have provided information and data regarding the detection of undesirable conditions. Herein, studies on tool condition monitoring are reviewed and classified. As Industry 4.0 penetrates all manufacturing sectors, the amount of manufacturing data generated has reached the level of big data, and classical artificial intelligence analyses are no longer adequate. Nevertheless, recent advances in deep learning methods have achieved revolutionary success in numerous industries. Deep multi-layer perceptron (DMLP), long-short-term memory (LSTM), convolutional neural network (CNN), and deep reinforcement learning (DRL) are among the most preferred methods of deep learning in recent years. As data size increases, these methods have shown promising performance improvement in prediction and learning, compared to classical artificial intelligence methods. This paper summarizes tool condition monitoring first, then presents the underlying theory of some of the most recent deep learning methods, and finally, attempts to identify new opportunities in tool condition monitoring, toward the realization of Industry 4.0.

Review of tool condition monitoring in machining and opportunities for deep learning

Abrasive Water Jet Machining process: A state of art of review

A systematic research into the cladding of stellite 6 on stainless steel by pulsed Nd:YAG laser has been carried out. The effects of pulse energy, pulse frequency, powder mass flow rate and spot overlap on the clad layer height, dilution and heat-affected zone (HAZ) have been examined. It was found that both the clad height and penetration into the substrate increase with the pulse energy, spot overlap and pulse frequency, but the effects of these parameters on dilution are complex. The dilution reaches the lowest value (4%) at the incident energy of 18 and 25 J/ pulse, spot overlap of 89% and pulse frequency of 40 Hz. The powder mass flow rate of 22 g/min (for energy of 25 J/pulse and spot overlap of 83%) produces thick clad layer with low dilution but results in the formation of defects. The hardness of the clad layer decreases linearly with increasing dilution. No cracks have been found in single-track clad layers at a spot overlap of 89%, however, cracks occurred at lower spot overlap. These cracks were eliminated by the multi-track cladding when the track increment is less than 1/3 of the width of track, which is believed to be due to the remelting or heat treatment of the previous clad track by the subsequent track. The track bands in multi-track clad show coarser structure, higher element segregation and lower hardness.

Pulsed Nd:YAG laser cladding of stellite 6 on stainless steel

Tool wear monitoring has been increasingly important in intelligent manufacturing to increase machining efficiency. Multi-domain features can effectively characterize tool wear condition, but manual feature fusion lowers monitoring efficiency and hinders the further improvement of predicting accuracy. In order to overcome these deficiencies, a new tool wear predicting method based on multi-domain feature fusion by deep convolutional neural network (DCNN) is proposed in this paper. In this method, multi-domain (including time-domain, frequency domain and time–frequency domain) features are respectively extracted from multisensory signals (e.g. three-dimensional cutting force and vibration) as health indictors of tool wear condition, then the relationship between these features and real-time tool wear is directly established based on the designed DCNN model to combine adaptive feature fusion with automatic continuous prediction. The performance of the proposed tool wear predicting method is experimentally validated by using three tool run-to-failure datasets measured from three-flute ball nose tungsten carbide cutter of high-speed CNC machine under dry milling operations. The experimental results show that the predicting accuracy of the proposed method is significantly higher than other advanced methods.

Tool wear predicting based on multi-domain feature fusion by deep convolutional neural network in milling operations

Investigation of signal behaviors for sensor fusion with tool condition monitoring system in turning

Wear resistance coatings of Stellite 6 were deposited on SS316 substrate by blending a buffer layer of Inconel 625 with varying Linear Heat Inputs (LHI). The mechanical and microstructural properties of Stellite 6 coatings are investigated to evaluate the effect of buffer layer. The surface flaws, microstructure, micro-hardness and wear resistance of Stellite 6 clads with buffer layer are studied and compared with direct deposited Stellite 6. The results show an increment in clad height by 30% and 9% at lower and higher LHIs, respectively as compared to pre-deposited Stellite 6 clads. The deposition pattern (with and without buffer) are free from surface and internal cracks. The dilution is reduced by 25% and 10% whereas the microhardness shown an improvement by 12% and 5% with addition of buffer layer. Further, a fine-grain microstructure is observed in buffer layer clads at the interface zone. Moreover, the studies on wear rate have shown improvement of 14% and 3%, respectively with low coefficient of friction (COF) in buffer layer deposition because of high microhardness and fine grain microstructure. Thus, laser cladding of Stellite 6 at lower LHI with buffer layer has shown excellent mechanical and microstructural properties.

Influence of buffer layer on surface and tribomechanical properties of laser cladded Stellite 6

The multi-layer laser cladding of high temperature resistance alloys i.e., Stellite 6 and Inconel 718 on SS316 was developed with an objective to investigate the effect of cladding materials on clad geometry, microstructure evolution and mechanical properties. The analysis was performed using Optical Microscope, SEM with EDS and Microhardness tester respectively. The results have shown a comparable difference in all the aspects of study. A 50% and 30% increment in clad height is measured while cladding at 12 mm/s and 16 mm/s scan speed as compared to 20 mm/s for both the alloys. The Inconel 718 deposits has shown 15–25% larger clad height, than Stellite 6. Also, under varying process parameters, 15–45% penetration depth and 10–15% higher dilution in Inconel 718 is obtained. SEM results have revealed that the microstructure evolution from top to bottom of the clad is nearly the same except at low laser powers. The decrement in microhardness is observed near the interface due to dilution and is higher in the first layer than the second layer. Whereas, the low dilution obtained in the second layer is because of the newly deposited layer over the substrate. The present work has given the optimum parameters (laser power and scan speed) as 2900 W and 20 mm/s for Stellite 6 and 3400 W, 12 mm/s for Inconel 718 respectively.

Effect of multi-layer laser cladding of Stellite 6 and Inconel 718 materials on clad geometry, microstructure evolution and mechanical properties

Influence of laser cladding parameters on distortion, thermal history and melt pool behaviour in multi-layer deposition of stellite 6: In-situ measurement

T.V.K. Gupta

Papers

Influence of buffer layer on surface and tribomechanical properties of laser cladded Stellite 6

Effect of multi-layer laser cladding of Stellite 6 and Inconel 718 materials on clad geometry, microstructure evolution and mechanical properties

Influence of laser cladding parameters on distortion, thermal history and melt pool behaviour in multi-layer deposition of stellite 6: In-situ measurement

A comprehensive review of free-form surface milling– Advances over a decade

Real Time Tool Wear Condition Monitoring in Hard Turning of Inconel 718 Using Sensor Fusion System